Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Dynamic Chunking for Diffusion Language Models
Yichen Zhu, Xiaoming Shi, Peng Zhao +3
Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoising from across-block condi…
cs.CL2026
When Latent Geometry Is Not Enough: Draft-Conditioned Latent Refinement for Non-Autoregressive Text Generation
De Shuai Zhang
Continuous diffusion and flow models are attractive for non-autoregressive text generation because they can update all positions in parallel. A major difficulty is the interface be…
cs.CL2024
Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models
Junfeng Tian, Da Zheng, Yang Cheng +3
Large language models (LLM) have prioritized expanding the context window from which models can incorporate more information. However, training models to handle long contexts prese…